Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2993 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1118417 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1095572 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5724. Min Act: -0.0000

Data Index: 627188 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5186. Min Act: -0.0000

Data Index: 701750 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4848. Min Act: -0.0000

Data Index: 703350 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4643. Min Act: -0.0000

Data Index: 669725 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1111453 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4394. Min Act: -0.0001

Data Index: 498514 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4654. Min Act: -0.0000

Data Index: 595552 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1359257 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4548. Min Act: -0.0001

Data Index: 255762 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4474. Min Act: -0.0000

Data Index: 963364 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1331083 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4094. Min Act: -0.0000

Data Index: 241096 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1285791 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4032. Min Act: -0.0000

Data Index: 609359 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4186. Min Act: -0.0000

Data Index: 606377 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4054. Min Act: -0.0000

Data Index: 868568 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1148281 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4330. Min Act: -0.0000

Data Index: 146971 (C4 (Web Text))

Max Activating Token Index: 852